Fairness and generalisability in deep learning of retinopathy of prematurity screening algorithms: a literature review.

Journal: BMJ open ophthalmology
PMID: 37558406

Abstract

BACKGROUND: Retinopathy of prematurity (ROP) is a vasoproliferative disease responsible for more than 30 000 blind children worldwide. Its diagnosis and treatment are challenging due to the lack of specialists, divergent diagnostic concordance and variation in classification standards. While artificial intelligence (AI) can address the shortage of professionals and provide more cost-effective management, its development needs fairness, generalisability and bias controls prior to deployment to avoid producing harmful unpredictable results. This review aims to compare AI and ROP study's characteristics, fairness and generalisability efforts.

Authors

  • Luis Filipe Nakayama
    São Paulo Federal University, São Paulo, SP, Brazil nakayama.luis@gmail.com.
  • William Greig Mitchell
    Department of Ophthalmology, Massachusetts Eye and Ear Infirmary, Boston, MA, USA.
  • Lucas Zago Ribeiro
    São Paulo Federal University, São Paulo, SP, Brazil.
  • Robyn Gayle Dychiao
    University of the Philippines Manila College of Medicine, Manila, Philippines.
  • Warachaya Phanphruk
    Department of Ophthalmology, Khon Kaen University, Nai Mueang, Thailand.
  • Leo Anthony Celi
    Massachusetts Institute of Technology, Cambridge, MA, USA.
  • Khumbo Kalua
    Department of Ophthalmology, Blantyre Institute for Community Ophthalmology, BICO, Blantyre, Malawi.
  • Alvina Pauline Dy Santiago
    Department of Ophthalmology and Visual Sciences, Philippine General Hospital, Manila, Philippines.
  • Caio Vinicius Saito Regatieri
    São Paulo Federal University, São Paulo, SP, Brazil.
  • Nilva Simeren Bueno Moraes
    Department of Ophthalmology, Sao Paulo Federal University, Sao Paulo, Brazil.

Keywords

External Resources

Popular Topics
Recent Journals